>>> 星瞳科技|OpenMV中国官方网站 <<<

>>> 星瞳科技店铺地址|OpenMV中国官方代理,全球九大代理商之一 <<<

>>> OpenMV3 Cam M7 官方高配版上市啦~戳我戳我戳我~ <<<

>>> 星瞳科技-OpenMV中文教程网 <<<

本例程为07-Face_Detection-face_detection.py
本例程的目的是利用haar算子实现人脸识别。

# Face Detection Example
#
# This example shows off the built-in face detection feature of the OpenMV Cam.
#
# Face detection works by using the Haar Cascade feature detector on an image. A
# Haar Cascade is a series of simple area contrasts checks. For the built-in
# frontalface detector there are 25 stages of checks with each stage having
# hundreds of checks a piece. Haar Cascades run fast because later stages are
# only evaluated if previous stages pass. Additionally, your OpenMV Cam uses
# a data structure called the integral image to quickly execute each area
# contrast check in constant time (the reason for feature detection being
# grayscale only is because of the space requirment for the integral image).

import sensor, time, image

# Reset sensor
sensor.reset()

# Sensor settings
sensor.set_contrast(1)
sensor.set_gainceiling(16)
# HQVGA and GRAYSCALE are the best for face tracking.
sensor.set_framesize(sensor.HQVGA)
sensor.set_pixformat(sensor.GRAYSCALE)
#注意人脸识别只能用灰度图哦

# Load Haar Cascade
# By default this will use all stages, lower satges is faster but less accurate.
face_cascade = image.HaarCascade("frontalface", stages=25)
#image.HaarCascade(path, stages=Auto)加载一个haar模型。haar模型是二进制文件,
#这个模型如果是自定义的,则引号内为模型文件的路径;也可以使用内置的haar模型,
#比如“frontalface” 人脸模型或者“eye”人眼模型。
#stages值未传入时使用默认的stages。stages值设置的小一些可以加速匹配,但会降低准确率。
print(face_cascade)

# FPS clock
clock = time.clock()

while (True):
    clock.tick()

    # Capture snapshot
    img = sensor.snapshot()

    # Find objects.
    # Note: Lower scale factor scales-down the image more and detects smaller objects.
    # Higher threshold results in a higher detection rate, with more false positives.
    objects = img.find_features(face_cascade, threshold=0.75, scale=1.35)
    #image.find_features(cascade, threshold=0.5, scale=1.5),thresholds越大,
    #匹配速度越快,错误率也会上升。scale可以缩放被匹配特征的大小。

    #在找到的目标上画框,标记出来
    # Draw objects
    for r in objects:
        img.draw_rectangle(r)

    # Print FPS.
    # Note: Actual FPS is higher, streaming the FB makes it slower.
    print(clock.fps())